时间序列论文趋势 2023–2026

主要结论

• 时间序列论文从 2023 年的 272 篇增长到 2026 年的 876 篇，三年间扩大到约 3.2 倍。
• NeurIPS 是发时间序列论文最多的会议，2023–2026 年共 757 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 85 篇。
• 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的分子建模是 2.7 倍，时间序列是 3.2 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026A Batched Hartigan's $k$-Means Clustering
• ICML 2026A Control-Theoretic View of Mamba on Stability and Robustness
• ICLR 2026A Single Architecture for Representing Invariance Under Any Space Group
• CVPR 2026Activation Matters Test-time Activated Negative Labels for OOD Detection with
• NeurIPS 2025Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency
• ICML 2025$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
• ICLR 2025A deep inverse-mapping model for a flapping robotic wing
• CVPR 2025Beyond Single-Modal Boundary: Cross-Modal Anomaly Detection through Visual Prototype and Harmonization
• NeurIPS 2024A Continuous-time Stochastic Gradient Descent Method for Continuous Data
• ICML 2024$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
• ICLR 2024ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
• CVPR 2024Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation
• NeurIPS 2023A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
• ICML 2023Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time
• ICLR 2023A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
• NeurIPS 2026A Locally Tokenized Generative Model for Robust Time-Series Watermarking
• ICML 2026ADHD Disease Detection Based on Short- and Long-Term Brain Function Encoding and Memory Graph Network
• ICLR 2026A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
• CVPR 2026Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis

全部时间序列论文

共 62 篇，第 1 / 2 页

1. ICML 2023A new near-linear time algorithm for k-nearest neighbor search using a compressed cover tree
2. ICML 2023Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time
3. ICML 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation
4. ICML 2023Adaptive Estimation of Graphical Models under Total Positivity
5. ICML 2023Adversarially Robust PAC Learnability of Real-Valued Functions
6. ICML 2023Bandits with Knapsacks: Advice on Time-Varying Demands
7. ICML 2023Bayesian online change point detection with Hilbert space approximate Student-t process
8. ICML 2023Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models
9. ICML 2023Context Consistency Regularization for Label Sparsity in Time Series
10. ICML 2023Deep Anomaly Detection under Labeling Budget Constraints
11. ICML 2023Deep Latent State Space Models for Time-Series Generation
12. ICML 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
13. ICML 2023Delayed Bandits: When Do Intermediate Observations Help?
14. ICML 2023Delving into Noisy Label Detection with Clean Data
15. ICML 2023Detecting Out-of-distribution Data through In-distribution Class Prior
16. ICML 2023Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
17. ICML 2023Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
18. ICML 2023Divide and Conquer Dynamic Programming: An Almost Linear Time Change Point Detection Methodology in High Dimensions
19. ICML 2023Domain Adaptation for Time Series Under Feature and Label Shifts
20. ICML 2023Dynamic Constrained Submodular Optimization with Polylogarithmic Update Time
21. ICML 2023Estimating the Contamination Factor's Distribution in Unsupervised Anomaly Detection
22. ICML 2023Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning
23. ICML 2023Fast Rates in Time-Varying Strongly Monotone Games
24. ICML 2023Feature Programming for Multivariate Time Series Prediction
25. ICML 2023Forget Unlearning: Towards True Data-Deletion in Machine Learning
26. ICML 2023Implicit Neural Spatial Representations for Time-dependent PDEs
27. ICML 2023Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks?
28. ICML 2023Learning Deep Time-index Models for Time Series Forecasting
29. ICML 2023Learning Perturbations to Explain Time Series Predictions
30. ICML 2023Leveraging Proxy of Training Data for Test-Time Adaptation
31. ICML 2023Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCA
32. ICML 2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series
33. ICML 2023Neural Stochastic Differential Games for Time-series Analysis
34. ICML 2023Non-autoregressive Conditional Diffusion Models for Time Series Prediction
35. ICML 2023Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
36. ICML 2023Nonparametric Density Estimation under Distribution Drift
37. ICML 2023ODS: Test-Time Adaptation in the Presence of Open-World Data Shift
38. ICML 2023On Distribution Dependent Sub-Logarithmic Query Time of Learned Indexing
39. ICML 2023On Enhancing Expressive Power via Compositions of Single Fixed-Size ReLU Network
40. ICML 2023On Pitfalls of Test-Time Adaptation
41. ICML 2023On the Statistical Benefits of Temporal Difference Learning
42. ICML 2023On the Stepwise Nature of Self-Supervised Learning
43. ICML 2023Optimal LP Rounding and Linear-Time Approximation Algorithms for Clustering Edge-Colored Hypergraphs
44. ICML 2023Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models
45. ICML 2023Predicting Ordinary Differential Equations with Transformers
46. ICML 2023Probabilistic Imputation for Time-series Classification with Missing Data
47. ICML 2023Prototype-oriented unsupervised anomaly detection for multivariate time series
48. ICML 2023Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation
49. ICML 2023Regularization-free Diffeomorphic Temporal Alignment Nets
50. ICML 2023Safe Offline Reinforcement Learning with Real-Time Budget Constraints

常见问题

2023–2026 年四大会议一共有多少篇时间序列论文？

共 2,157 篇，按年份分别是 2023 年 272 篇、2024 年 424 篇、2025 年 585 篇、2026 年 876 篇。

NeurIPS 2026 有多少篇时间序列论文？

NeurIPS 2026 有 298 篇时间序列论文，上一届是 221 篇。

ICLR 2026 有多少篇时间序列论文？

ICLR 2026 有 220 篇时间序列论文，上一届是 131 篇。

ICML 2026 有多少篇时间序列论文？

ICML 2026 有 264 篇时间序列论文，上一届是 159 篇。

CVPR 2026 有多少篇时间序列论文？

CVPR 2026 有 94 篇时间序列论文，上一届是 74 篇。

哪个会议的时间序列论文最多？

NeurIPS，2023–2026 年共 757 篇。